{"id":"https://openalex.org/W2081841744","doi":"https://doi.org/10.1145/1452392.1452446","title":"A realtime multimodal system for analyzing group meetings by combining face pose tracking and speaker diarization","display_name":"A realtime multimodal system for analyzing group meetings by combining face pose tracking and speaker diarization","publication_year":2008,"publication_date":"2008-10-20","ids":{"openalex":"https://openalex.org/W2081841744","doi":"https://doi.org/10.1145/1452392.1452446","mag":"2081841744"},"language":"en","primary_location":{"id":"doi:10.1145/1452392.1452446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1452392.1452446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on Multimodal interfaces","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014373252","display_name":"Kazuhiro Otsuka","orcid":"https://orcid.org/0000-0003-4352-3955"},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Otsuka","raw_affiliation_strings":["NTT Communication Science Labs, Atsugi, Japan","NTT Communication Science Laboratories, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, Atsugi, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309584","display_name":"Shoko Araki","orcid":"https://orcid.org/0000-0003-4363-4305"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoko Araki","raw_affiliation_strings":["NTT Communication Science Labs, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066431676","display_name":"Kentaro Ishizuka","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kentaro Ishizuka","raw_affiliation_strings":["NTT Communication Science Labs, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Labs, Kyoto, Japan","[NTT Communication Science Laboratories, Kyoto, Japan]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[NTT Communication Science Laboratories, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068912095","display_name":"Martin Heinrich","orcid":"https://orcid.org/0000-0003-0858-1551"},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Martin Heinrich","raw_affiliation_strings":["NTT Communication Science Labs, Atsugi, Japan","NTT Communication Science Laboratories, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, Atsugi, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017815880","display_name":"Junji Yamato","orcid":"https://orcid.org/0000-0003-1634-7984"},"institutions":[{"id":"https://openalex.org/I4210105847","display_name":"NTT Basic Research Laboratories","ror":"https://ror.org/01m2pas06","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210105847"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junji Yamato","raw_affiliation_strings":["NTT Communication Science Labs, Atsugi, Japan","NTT Communication Science Laboratories, Atsugi, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Labs, Atsugi, Japan","institution_ids":[]},{"raw_affiliation_string":"NTT Communication Science Laboratories, Atsugi, Japan","institution_ids":["https://openalex.org/I4210105847"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":10.7586,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":{"value":0.99099374,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"257","last_page":"264"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8015428781509399},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7310649156570435},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6218298077583313},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5990884900093079},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5917142629623413},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5779218077659607},{"id":"https://openalex.org/keywords/omnidirectional-camera","display_name":"Omnidirectional camera","score":0.5463758111000061},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5332229733467102},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5031630396842957},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.48325997591018677},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.4638773202896118},{"id":"https://openalex.org/keywords/facial-motion-capture","display_name":"Facial motion capture","score":0.44964325428009033},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.39479759335517883},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.38363996148109436},{"id":"https://openalex.org/keywords/omnidirectional-antenna","display_name":"Omnidirectional antenna","score":0.35745078325271606},{"id":"https://openalex.org/keywords/face-detection","display_name":"Face detection","score":0.3187779188156128},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.30669736862182617},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.23022323846817017}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8015428781509399},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7310649156570435},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6218298077583313},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5990884900093079},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5917142629623413},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5779218077659607},{"id":"https://openalex.org/C2777953668","wikidata":"https://www.wikidata.org/wiki/Q684116","display_name":"Omnidirectional camera","level":4,"score":0.5463758111000061},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5332229733467102},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5031630396842957},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.48325997591018677},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.4638773202896118},{"id":"https://openalex.org/C98907195","wikidata":"https://www.wikidata.org/wiki/Q5428562","display_name":"Facial motion capture","level":5,"score":0.44964325428009033},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.39479759335517883},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.38363996148109436},{"id":"https://openalex.org/C24027999","wikidata":"https://www.wikidata.org/wiki/Q2176348","display_name":"Omnidirectional antenna","level":3,"score":0.35745078325271606},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.3187779188156128},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.30669736862182617},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.23022323846817017},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0},{"id":"https://openalex.org/C21822782","wikidata":"https://www.wikidata.org/wiki/Q131214","display_name":"Antenna (radio)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1452392.1452446","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1452392.1452446","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th international conference on Multimodal interfaces","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W107298650","https://openalex.org/W1493372482","https://openalex.org/W1514030638","https://openalex.org/W1519717339","https://openalex.org/W1534102188","https://openalex.org/W1588191538","https://openalex.org/W1591474362","https://openalex.org/W1592567216","https://openalex.org/W1965773733","https://openalex.org/W1985479696","https://openalex.org/W2043393794","https://openalex.org/W2046317813","https://openalex.org/W2099599499","https://openalex.org/W2103738385","https://openalex.org/W2115011265","https://openalex.org/W2116516796","https://openalex.org/W2118924889","https://openalex.org/W2141398670","https://openalex.org/W2141708364","https://openalex.org/W2170579896","https://openalex.org/W2171092607","https://openalex.org/W2965385724","https://openalex.org/W3097096317","https://openalex.org/W4285719527","https://openalex.org/W6767111255"],"related_works":["https://openalex.org/W4307477878","https://openalex.org/W53042703","https://openalex.org/W2080594779","https://openalex.org/W2375878039","https://openalex.org/W2741165524","https://openalex.org/W2368198420","https://openalex.org/W2004195487","https://openalex.org/W3101807488","https://openalex.org/W2390289544","https://openalex.org/W2735361994"],"abstract_inverted_index":{"This":[0,157],"paper":[1,158],"presents":[2,160],"a":[3,12,47,67,140,146],"realtime":[4,97],"system":[5,186],"for":[6,52,165,178,182,194],"analyzing":[7],"group":[8],"meetings":[9,54],"that":[10],"uses":[11],"novel":[13,48],"omnidirectional":[14,74],"camera-microphone":[15],"system.":[16],"The":[17,109],"goal":[18],"is":[19,31,42,55,118,136],"to":[20,37,120],"automatically":[21],"discover":[22],"the":[23,78,80,115,122,127,130,169,185],"visual":[24],"focus":[25,123],"of":[26,59,84,100,124,149,171],"attention":[27,125],"(VFOA),":[28],"i.e.":[29,40],"\"who":[30,41],"looking":[32],"at":[33,188],"whom\",":[34],"in":[35,126],"addition":[36],"speaker":[38,134],"diarization,":[39],"speaking":[43],"and":[44,66,82,145,168,180],"when\".":[45],"First,":[46],"tabletop":[49],"sensing":[50],"device":[51],"round-table":[53],"presented;":[56],"it":[57,95],"consists":[58],"two":[60,63,175],"cameras":[61],"with":[62,77],"fisheye":[64],"lenses":[65],"triangular":[68],"microphone":[69,131],"array.":[70],"Second,":[71],"from":[72],"high-resolution":[73],"images":[75],"captured":[76],"cameras,":[79],"position":[81],"pose":[83],"people's":[85],"faces":[86,102],"are":[87],"estimated":[88],"by":[89,103,114,139,153],"STCTracker":[90],"(Sparse":[91],"Template":[92],"Condensation":[93],"Tracker);":[94],"realizes":[96],"robust":[98,133],"tracking":[99],"multiple":[101],"utilizing":[104],"GPUs":[105],"(Graphics":[106],"Processing":[107],"Units).":[108],"face":[110,116],"position/pose":[111],"data":[112],"output":[113],"tracker":[117],"used":[119],"estimate":[121],"group.":[128],"Using":[129,174],"array,":[132],"diarization":[135],"carried":[137],"out":[138],"VAD":[141],"(Voice":[142],"Activity":[143],"Detection)":[144],"DOA":[147],"(Direction":[148],"Arrival)":[150],"estimation":[151],"followed":[152],"sound":[154],"source":[155],"clustering.":[156],"also":[159],"new":[161],"3-D":[162],"visualization":[163],"schemes":[164],"meeting":[166],"scenes":[167],"results":[170],"an":[172],"analysis.":[173],"PCs,":[176],"one":[177,181],"vision":[179],"audio":[183],"processing,":[184],"runs":[187],"about":[189],"20":[190],"frames":[191],"per":[192],"second":[193],"5-person":[195],"meetings.":[196]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
